Push agent to the Hub

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 219.40 +/- 130.80
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  ```python
+  {'total_timesteps': 250000
+'learning_rate': 0.02
+'num_envs': 8
+'num_steps': 256
+'anneal_lr': True
+'gae': True
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 4
+'update_epochs': 4
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'batch_size': 2048
+'minibatch_size': 512
+'env_id': 'LunarLander-v2'
+'name': 'ppo'
+'seed': 1
+'torch_deterministic': False
+'cuda': True
+'track': False
+'wandb_project_name': 'hf-deep-rl-ppo'
+'wandb_entity': None
+'capture_video': False
+'repo_id': 'bguisard/PPO-cleanrl-LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1677372657.bguisards-MBP.3672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d760006a8f720fdd7e6a4c18aa97ecd51b957e8581ae0a7355f2dbb2c89c7a77
+size 191635

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fbb2e6aa7f0083d0d00e3b957b819ac82a06bbeb57e85dfe92c3cd5e94d8d1f
+size 42469

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 219.40319837721307, "std_reward": 130.79869418541, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T19:53:39.029379"}